Context recognition for hierarchical text classification Export

@article{citeulike:3979048, abstract = {Information is often organized as a text hierarchy. A hierarchical text-classification system is thus essential for the management, sharing, and dissemination of information. It aims to automatically classify each incoming document into zero, one, or several categories in the text hierarchy. In this paper, we present a technique called CRHTC (context recognition for hierarchical text classification) that performs hierarchical text classification by recognizing the context of discussion (COD) of each category. A category's COD is governed by its ancestor categories, whose contents indicate contextual backgrounds of the category. A document may be classified into a category only if its content matches the category's COD. CRHTC does not require any trials to manually set parameters, and hence is more portable and easier to implement than other methods. It is empirically evaluated under various conditions. The results show that CRHTC achieves both better and more stable performance than several hierarchical and nonhierarchical text-classification methodologies.}, address = {Department of Medical Informatics, Tzu Chi University, Hualien, Taiwan, ROC}, author = {Liu, Rey-Long}, citeulike-article-id = {3979048}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/asi.21022}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/121664871/ABSTRACT}, doi = {10.1002/asi.21022}, journal = {Journal of the American Society for Information Science and Technology}, keywords = {categories, classification, context, context\_dependent, hierarchy, ontology}, number = {9999}, pages = {NA+}, posted-at = {2009-01-29 14:09:29}, priority = {2}, title = {Context recognition for hierarchical text classification}, url = {http://dx.doi.org/10.1002/asi.21022}, volume = {9999}, year = {2009} }

TY - JOUR ID - citeulike:3979048 L3 - citeulike-article-id:3979048 N2 - Information is often organized as a text hierarchy. A hierarchical text-classification system is thus essential for the management, sharing, and dissemination of information. It aims to automatically classify each incoming document into zero, one, or several categories in the text hierarchy. In this paper, we present a technique called CRHTC (context recognition for hierarchical text classification) that performs hierarchical text classification by recognizing the context of discussion (COD) of each category. A category's COD is governed by its ancestor categories, whose contents indicate contextual backgrounds of the category. A document may be classified into a category only if its content matches the category's COD. CRHTC does not require any trials to manually set parameters, and hence is more portable and easier to implement than other methods. It is empirically evaluated under various conditions. The results show that CRHTC achieves both better and more stable performance than several hierarchical and nonhierarchical text-classification methodologies. IS - 9999 JF - Journal of the American Society for Information Science and Technology AD - Department of Medical Informatics, Tzu Chi University, Hualien, Taiwan, ROC TI - Context recognition for hierarchical text classification VL - 9999 SP - NA KW - categories KW - classification KW - context KW - context_dependent KW - hierarchy KW - ontology AU - Liu, Rey-Long PY - 2009/// UR - http://dx.doi.org/10.1002/asi.21022 ER -